Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of siblings, specifically sisters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "sister" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustomed
    -0.72
    ered
    -0.69
    veyard
    -0.68
    assic
    -0.67
    uden
    -0.63
    tarians
    -0.63
    ech
    -0.62
    ankind
    -0.62
    erers
    -0.62
    ustom
    -0.61
    POSITIVE LOGITS
    hood
    1.21
    heses
    0.92
     sister
    0.91
    hips
    0.88
     sisters
    0.85
    folk
    0.85
    hesis
    0.83
    nets
    0.75
     Sister
    0.74
     Carol
    0.73
    Act Density 0.021%

    No Known Activations